bjztckb402

基于Powell和互信息的多分辨率图像配准(Image registration Powell and mutual information)

说明：  该程序通过雅可比矩阵求解Rossler系统的李雅普诺夫指数指数，并绘制了其频谱图。(The program solves the Lyapunov exponent of Rossler system by Jacobian matrix and draws its spectrum.)

Image Watershed Segmentation图像边缘提取(Image Watershed Segmentation Image Edge Detection)

基于核的相关滤波跟踪方法，最新的，TPMAI上的文章，速度超级快！(This MATLAB code implements a simple tracking pipeline based on the Kernelized Correlation Filter (KCF), and Dual Correlation Filter (DCF).)

图像巴特沃斯陷波器，实现了简单的巴特沃斯陷波器滤除图像的某些频率的干扰(Image Butterworth notch filter, to achieve a simple Butterworth notch filter to filter out images of certain frequency interference)

用块匹配法进行运动估计的matlab实现方法，返回运动矩阵(block matching method used for motion estimation method of Matlab, the return movement Matrix)

基于visual c++平台，相机标定方法中的直接线性变换方法，即DLT方法(Based on visual c++ platform, camera calibration method of direct linear transformation method, namely DLT method)

关于MC三维重建算法的二义性消除的文章，很好的消除了MC算法中的二义性(it s the article about Three-dimensional reconstruction algorithm to eliminate ambiguity in MC)

图像检测的算法，Faster R-CNN算法，先对整张图像进行卷积计算，然后通过感兴趣区域池化层(RoI Pooling Layer)将选择性搜索算法推荐出来的候选区域和卷积网络计算出的特征映射图进行融合，得到候选区域对应的特征矢量，这种共享卷积计算的操作极大地减少了卷积计算的次数。而且这些特征矢量的维度统一，方便后续的分类工作。通过感兴趣区域池化层处理卷积特征，并将得到的特征送往两个并行计算任务进行训练，分类和定位回归。通过这些方法和改进的框架，Fast R-CNN 用更短的训练和测试时长，取得了比 R-CNN 更好的效果(Faster R-CNN algorithm first convolutes the whole image, then fuses the candidate regions recommended by the selective search algorithm and the feature mapping maps calculated by the convolution network through the RoI Pooling Layer to get the corresponding feature vectors of the candidate regions, which greatly reduces the number of convolution calculations. Moreover, the dimension of these feature vectors is unified, which facilitates the subsequent classification work. The convolution feature is processed by the pooling layer of the region of interest, and the obtained feature is sent to two parallel computing tasks for training, classification and positioning regression. Through these methods and improved framework, Fast R-CNN uses shorter training and testing time and achieves better results than R-CNN.)

文献 "Deblurring Text Images via L0-Regularized Intensity and Gradient Prior" 的参考代码 用Lp正则化方法做盲复原的代码 demo_text_deblurring 是主函数(refer to "Deblurring Text Images via L0-Regularized Intensity and Gradient Prior" main function: demo_text_deblurring)